{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:29:24Z","timestamp":1792790964937,"version":"4.5.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,2,17]],"date-time":"2021-02-17T00:00:00Z","timestamp":1613520000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,2,17]],"date-time":"2021-02-17T00:00:00Z","timestamp":1613520000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100003500","name":"University of Padua","doi-asserted-by":"crossref","award":["Talents in Research@University of Padua"],"award-info":[{"award-number":["Talents in Research@University of Padua"]}],"id":[{"id":"10.13039\/501100003500","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Department of Animal Medicine, Production and Health-MAPS, University of Padua","award":["SID-Banzato 2019"],"award-info":[{"award-number":["SID-Banzato 2019"]}],"id":[{"id":"https:\/\/ror.org\/00240q980","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Department of Animal Medicine, Production and Health-MAPS","award":["SID-Zotti 2018"],"award-info":[{"award-number":["SID-Zotti 2018"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The interpretation of thoracic radiographs is a challenging and error-prone task for veterinarians. Despite recent advancements in machine learning and computer vision, the development of computer-aided diagnostic systems for radiographs remains a challenging and unsolved problem, particularly in the context of veterinary medicine. In this study, a novel method, based on multi-label deep convolutional neural network (CNN), for the classification of thoracic radiographs in dogs was developed. All the thoracic radiographs of dogs performed between 2010 and 2020 in the institution were retrospectively collected. Radiographs were taken with two different radiograph acquisition systems and were divided into two data sets accordingly. One data set (Data Set 1) was used for training and testing and another data set (Data Set 2) was used to test the generalization ability of the CNNs. Radiographic findings used as non mutually exclusive labels to train the CNNs were: unremarkable, cardiomegaly, alveolar pattern, bronchial pattern, interstitial pattern, mass, pleural effusion, pneumothorax, and megaesophagus. Two different CNNs, based on ResNet-50 and DenseNet-121 architectures respectively, were developed and tested. The CNN based on ResNet-50 had an Area Under the Receive-Operator Curve (AUC) above 0.8 for all the included radiographic findings except for bronchial and interstitial patterns both on Data Set 1 and Data Set 2. The CNN based on DenseNet-121 had a lower overall performance. Statistically significant differences in the generalization ability between the two CNNs were evident, with the CNN based on ResNet-50 showing better performance for alveolar pattern, interstitial pattern, megaesophagus, and pneumothorax.<\/jats:p>","DOI":"10.1038\/s41598-021-83515-3","type":"journal-article","created":{"date-parts":[[2021,2,19]],"date-time":"2021-02-19T11:46:37Z","timestamp":1613735197000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":58,"title":["Automatic classification of canine thoracic radiographs using deep learning"],"prefix":"10.1038","volume":"11","author":[{"given":"Tommaso","family":"Banzato","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marek","family":"Wodzinski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Silvia","family":"Burti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Valentina Longhin","family":"Osti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Valentina","family":"Rossoni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manfredo","family":"Atzori","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessandro","family":"Zotti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,2,17]]},"reference":[{"key":"83515_CR1","doi-asserted-by":"publisher","first-page":"1668","DOI":"10.1148\/rg.2015150023","volume":"35","author":"MA Bruno","year":"2015","unstructured":"Bruno, M. A., Walker, E. A. & Abujudeh, H. H. Understanding and confronting our mistakes: The epidemiology of error in radiology and strategies for error reduction. RadioGraphics 35, 1668\u20131676. https:\/\/doi.org\/10.1148\/rg.2015150023 (2015).","journal-title":"RadioGraphics"},{"key":"83515_CR2","doi-asserted-by":"publisher","first-page":"1173","DOI":"10.2214\/ajr.06.1270","volume":"188","author":"L Berlin","year":"2007","unstructured":"Berlin, L. Accuracy of diagnostic procedures: Has it improved over the past five decades?. Am. J. Roentgenol. 188, 1173\u20131178. https:\/\/doi.org\/10.2214\/ajr.06.1270 (2007).","journal-title":"Am. J. Roentgenol."},{"key":"83515_CR3","first-page":"533","volume":"51","author":"K Alexander","year":"2010","unstructured":"Alexander, K. Reducing error in radiographic interpretation. Can. Vet. J. 51, 533\u2013536 (2010).","journal-title":"Can. Vet. J."},{"key":"83515_CR4","doi-asserted-by":"publisher","first-page":"2513","DOI":"10.5433\/1679-0359.2014v35n5p2513","volume":"35","author":"T.\u00a0R Froes","year":"2014","unstructured":"Froes, T. .\u00a0R. et al. Interobserver agreement in interpretation of radiographic pulmonary changes in dogs in relation to radiology training. Sem. Cienc. Agrarias 35, 2513\u20132526. https:\/\/doi.org\/10.5433\/1679-0359.2014v35n5p2513 (2014).","journal-title":"Sem. Cienc. Agrarias"},{"key":"83515_CR5","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1136\/pmj.79.930.214","volume":"79","author":"ME Gatt","year":"2003","unstructured":"Gatt, M. E., Spectre, G., Paltiel, O., Hiller, N. & Stalnikowicz, R. Chest radiographs in the emergency department: Is the radiologist really necessary?. Postgrad. Med. J. 79, 214\u2013217. https:\/\/doi.org\/10.1136\/pmj.79.930.214 (2003).","journal-title":"Postgrad. Med. J."},{"key":"83515_CR6","doi-asserted-by":"publisher","first-page":"739","DOI":"10.2214\/ajr.16.16963","volume":"208","author":"S Waite","year":"2016","unstructured":"Waite, S. et al. Interpretive error in radiology. Am. J. Roentgenol. 208, 739\u2013749. https:\/\/doi.org\/10.2214\/ajr.16.16963 (2016).","journal-title":"Am. J. Roentgenol."},{"key":"83515_CR7","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1148\/radiol.2016150409","volume":"280","author":"BS Kelly","year":"2016","unstructured":"Kelly, B. S., Rainford, L. A., Darcy, S. P., Kavanagh, E. C. & Toomey, R. J. The development of expertise in radiology: In chest radiograph interpretation, \u201cexpert\u2019\u2019 search pattern may predate \u201cexpert\u2019\u2019 levels of diagnostic accuracy for pneumothorax identification. Radiology 280, 252\u2013260. https:\/\/doi.org\/10.1148\/radiol.2016150409 (2016).","journal-title":"Radiology"},{"key":"83515_CR8","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1007\/s10459-009-9182-2","volume":"14","author":"P Croskerry","year":"2009","unstructured":"Croskerry, P. Clinical cognition and diagnostic error: Applications of a dual process model of reasoning. Adv. Heal. Sci. Educ. 14, 27\u201335. https:\/\/doi.org\/10.1007\/s10459-009-9182-2 (2009).","journal-title":"Adv. Heal. Sci. Educ."},{"key":"83515_CR9","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1148\/radiol.2019182465","volume":"294","author":"Y Sim","year":"2020","unstructured":"Sim, Y. et al. Deep convolutional neural network-based software improves radiologist detection of malignant lung nodules on chest radiographs. Radiology 294, 199\u2013209. https:\/\/doi.org\/10.1148\/radiol.2019182465 (2020).","journal-title":"Radiology"},{"key":"83515_CR10","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1371\/journal.pmed.1002707","volume":"15","author":"K Yasaka","year":"2018","unstructured":"Yasaka, K. & Abe, O. Deep learning and artificial intelligence in radiology: Current applications and future directions. PLoS Med. 15, 2\u20135. https:\/\/doi.org\/10.1371\/journal.pmed.1002707 (2018).","journal-title":"PLoS Med."},{"key":"83515_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pmed.1002697","volume":"15","author":"AG Taylor","year":"2018","unstructured":"Taylor, A. G., Mielke, C. & Mongan, J. Automated detection of moderate and large pneumothorax on frontal chest X-rays using deep convolutional neural networks: A retrospective study. PLoS Med. 15, 1\u201315. https:\/\/doi.org\/10.1371\/journal.pmed.1002697 (2018).","journal-title":"PLoS Med."},{"key":"83515_CR12","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1148\/radiol.2017162326","volume":"284","author":"P Lakhani","year":"2017","unstructured":"Lakhani, P. & Sundaram, B. Deep learning at chest radiography: Automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology 284, 574\u2013582. https:\/\/doi.org\/10.1148\/radiol.2017162326 (2017).","journal-title":"Radiology"},{"key":"83515_CR13","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1148\/radiol.2018180237","volume":"290","author":"JG Nam","year":"2019","unstructured":"Nam, J. G. et al. Development and validation of deep learning-based automatic detection algorithm for malignant pulmonary nodules on chest radiographs. Radiology 290, 218\u2013228. https:\/\/doi.org\/10.1148\/radiol.2018180237 (2019).","journal-title":"Radiology"},{"key":"83515_CR14","doi-asserted-by":"publisher","unstructured":"Murphy, K. et al. COVID-19 on the chest radiograph: A multi-reader evaluation of an AI system. Radiology 201874, https:\/\/doi.org\/10.1148\/radiol.2020201874 (2020).","DOI":"10.1148\/radiol.2020201874"},{"key":"83515_CR15","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1148\/radiol.2018180921","volume":"291","author":"M Annarumma","year":"2019","unstructured":"Annarumma, M. et al. Automated triaging of adult chest radiographs with deep artificial neural networks. Radiology 291, 196\u2013202. https:\/\/doi.org\/10.1148\/radiol.2018180921 (2019).","journal-title":"Radiology"},{"key":"83515_CR16","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1097\/RLI.0000000000000341","volume":"52","author":"M Cicero","year":"2017","unstructured":"Cicero, M. et al. Training and validating a deep convolutional neural network for computer-aided detection and classification of abnormalities on frontal chest radiographs. Invest. Radiol. 52, 281\u2013287. https:\/\/doi.org\/10.1097\/RLI.0000000000000341 (2017).","journal-title":"Invest. Radiol."},{"key":"83515_CR17","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1186\/s12917-018-1638-2","volume":"14","author":"T Banzato","year":"2018","unstructured":"Banzato, T., Bernardini, M., Cherubini, G. B. & Zotti, A. A methodological approach for deep learning to distinguish between meningiomas and gliomas on canine MR-images. BMC Vet. Res. 14, 317. https:\/\/doi.org\/10.1186\/s12917-018-1638-2 (2018).","journal-title":"BMC Vet. Res."},{"key":"83515_CR18","doi-asserted-by":"publisher","unstructured":"Banzato, T. et al. Accuracy of deep learning to differentiate the histopathological grading of meningiomas on MR images: A preliminary study. J. Magnet. Resonan. Imaging. https:\/\/doi.org\/10.1002\/jmri.26723 (2019).","DOI":"10.1002\/jmri.26723"},{"key":"83515_CR19","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/j.tvjl.2017.12.026","volume":"233","author":"T Banzato","year":"2018","unstructured":"Banzato, T. et al. Use of transfer learning to detect diffuse degenerative hepatic diseases from ultrasound images in dogs: A methodological study. Vet. J. 233, 35\u201340. https:\/\/doi.org\/10.1016\/j.tvjl.2017.12.026 (2018).","journal-title":"Vet. J."},{"key":"83515_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-019-50437-0","volume":"9","author":"JY Kim","year":"2019","unstructured":"Kim, J. Y., Lee, H. E., Choi, Y. H., Lee, S. J. & Jeon, J. S. CNN-based diagnosis models for canine ulcerative keratitis. Sci. Rep. 9, 1\u20137. https:\/\/doi.org\/10.1038\/s41598-019-50437-0 (2019).","journal-title":"Sci. Rep."},{"key":"83515_CR21","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1016\/j.patrec.2018.10.027","volume":"130","author":"Q Guan","year":"2020","unstructured":"Guan, Q. & Huang, Y. Multi-label chest X-ray image classification via category-wise residual attention learning. Pattern Recognit. Lett. 130, 259\u2013266. https:\/\/doi.org\/10.1016\/j.patrec.2018.10.027 (2020).","journal-title":"Pattern Recognit. Lett."},{"key":"83515_CR22","doi-asserted-by":"publisher","first-page":"105505","DOI":"10.1016\/j.tvjl.2020.105505","volume":"262","author":"S Burti","year":"2020","unstructured":"Burti, S., Osti, V. L., Zotti, A. & Banzato, T. Use of deep learning to detect cardiomegaly on thoracic radiographs in dogs. Vet. J. 262, 105505. https:\/\/doi.org\/10.1016\/j.tvjl.2020.105505 (2020).","journal-title":"Vet. J."},{"key":"83515_CR23","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1111\/vru.12901","volume":"61","author":"S Li","year":"2020","unstructured":"Li, S., Wang, Z., Visser, L. C., Wisner, E. R. & Cheng, H. Pilot study: Application of artificial intelligence for detecting left atrial enlargement on canine thoracic radiographs. Vet. Radiol. Ultrasound 61, 611\u2013618. https:\/\/doi.org\/10.1111\/vru.12901 (2020).","journal-title":"Vet. Radiol. Ultrasound"},{"key":"83515_CR24","doi-asserted-by":"publisher","unstructured":"Wang, X. et\u00a0al. ChestX-ray8: Hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. in Proceedings of the 30th IEEE Conference on Computer Visual Pattern Recognition, CVPR 2017 Vol. 2017, 3462\u20133471, https:\/\/doi.org\/10.1109\/CVPR.2017.369 (2017). arXiv:1705.02315.","DOI":"10.1109\/CVPR.2017.369"},{"key":"83515_CR25","doi-asserted-by":"publisher","unstructured":"Baltruschat, I.\u00a0M., Nickisch, H., Grass, M., Knopp, T. & Saalbach, A. Comparison of deep learning approaches for multi-label chest X-ray classification. Sci. Rep. 9, 1\u201310, https:\/\/doi.org\/10.1038\/s41598-019-42294-8 (2019). arXiv:1803.02315.","DOI":"10.1038\/s41598-019-42294-8"},{"key":"83515_CR26","unstructured":"Yao, L., Prosky, J., Poblenz, E., Covington, B. & Lyman, K. Weakly supervised medical diagnosis and localization from multiple resolutions. arXiV Preprint: arXiv:1803.07703 (2018)."},{"key":"83515_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pmed.1002683","volume":"15","author":"JR Zech","year":"2018","unstructured":"Zech, J. R. et al. Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: A cross-sectional study. PLoS Med. 15, 1\u201317. https:\/\/doi.org\/10.1371\/journal.pmed.1002683 (2018).","journal-title":"PLoS Med."},{"key":"83515_CR28","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1016\/S0195-5616(00)50027-8","volume":"30","author":"W.\u00a0B. James","year":"2000","unstructured":"James, W. .\u00a0B. . Vertebral scale system to measure heart size in radiographs. Vet. Clin. N. Am. Small Anim. Pract. 30, 379\u2013393. https:\/\/doi.org\/10.1016\/S0195-5616(00)50027-8 (2000).","journal-title":"Vet. Clin. N. Am. Small Anim. Pract."},{"key":"83515_CR29","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z. & Weinberger, K. Densely connected convolutional networks. CoRRarXiv:1608.06993 (2016).","DOI":"10.1109\/CVPR.2017.243"},{"key":"83515_CR30","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. in IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) 2016, Vol. 2016, 770\u2013778 (2016).","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-83515-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-83515-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-83515-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,2]],"date-time":"2022-12-02T22:52:30Z","timestamp":1670021550000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-83515-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,17]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["83515"],"URL":"https:\/\/doi.org\/10.1038\/s41598-021-83515-3","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2,17]]},"assertion":[{"value":"18 September 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 February 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 February 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"3964"}}